web3-data-skill
Analysis
The artifacts show a coherent Chainbase Web3 data-query skill with disclosed external API use and an optional API key, with no evidence of hidden persistence, destructive actions, or off-purpose exfiltration.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
endpoint="$1" ... --method=*) method="${arg#--method=}" ... --body=*) body="${arg#--body=}"The wrapper lets the agent choose Chainbase API paths, methods, and request bodies. This is broad tool authority, but it remains bounded to Chainbase domains and matches the skill's stated data-query purpose.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
API_KEY="${CHAINBASE_API_KEY:-demo}" ... -H "${call_header}: ${API_KEY}"The script reads an optional Chainbase API key from the environment and sends it as an API header to Chainbase. This is expected for the service and no artifact shows the key being logged or sent elsewhere.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
BASE_URL="https://api.chainbase.online" ... SQL_BASE_URL="https://api.chainbase.com/api/v1" ... curl -s
The skill sends wallet addresses, token contracts, SQL queries, and related request parameters to the external Chainbase provider. This data flow is disclosed and central to the skill.